当前位置: X-MOL 学术Neural Process Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
GrasNet: A Simple Grassmannian Network for Image Set Classification
Neural Processing Letters ( IF 3.1 ) Pub Date : 2020-06-17 , DOI: 10.1007/s11063-020-10276-x
Rui Wang , Xiao-Jun Wu

Representing image sets on the Grassmann manifold has been widely used in visual classification tasks, and the existing Grassmannian learning methods have shown powerful ability in feature representation. In order to develop the ideology of conventional deep learning to the Grassmann manifold, we devise a simple Grassmann manifold feature learning network (GrasNet) in this paper, which provides a new way for image set classification. For the proposed GrasNet, we design a fully mapping layer to transform the input Grassmannian data into more appropriate representations. In view of the consistency of the data space, orthonormal maintaining layer is exploited to normalize the input matrices to form a valid Grassmann manifold. To perform Grassmannian computing on the resulting Grassmann manifold-valued features, we also introduce a projection mapping layer. For the sake of further reducing the dimensionality and redundancy of the learned geometric features, we devise a projection pooling layer. The log-map layer is finally adopted to embed the resulting data manifold into a tangent space via Riemannian matrix logarithm map, such that the Euclidean computations apply. To learn the multistage connection weights for the proposed GrasNet, we utilize the Principal Component Analysis (PCA) algorithm rather than the complex Riemannian matrix backpropagation optimizer, which makes it be built and trained extremely easy and efficient. We evaluate our model on three different visual classification tasks: face recognition, object categorization and cell identification, respectively. Extensive classification results verify its feasibility and effectiveness.

中文翻译:

GrasNet:用于图像集分类的简单格拉斯曼网络

在格拉斯曼流形上表示图像集已广泛用于视觉分类任务,现有的格拉斯曼学习方法在特征表示中具有强大的能力。为了向格拉斯曼流形发展常规深度学习的思想,本文设计了一个简单的格拉斯曼流形特征学习网络(GrasNet),为图像集分类提供了一种新的方法。对于建议的GrasNet,我们设计了一个完全映射层,将输入的Grassmannian数据转换为更合适的表示形式。考虑到数据空间的一致性,利用正交保持层对输入矩阵进行归一化以形成有效的格拉斯曼流形。要对产生的Grassmann流形值特征执行Grassmannian计算,我们还介绍了投影映射层。为了进一步降低学习的几何特征的维数和冗余度,我们设计了一个投影池层。最终采用对数图层,通过黎曼矩阵对数图将所得数据流形嵌入到切线空间中,从而应用欧几里得计算。要了解所建议的GrasNet的多级连接权重,我们使用主成分分析(PCA)算法,而不是复杂的黎曼矩阵反向传播优化器,这使得它的构建和训练极为容易和高效。我们在三种不同的视觉分类任务上评估我们的模型:分别是人脸识别,物体分类和细胞识别。大量的分类结果证明了其可行性和有效性。为了进一步降低学习的几何特征的维数和冗余度,我们设计了一个投影池层。最终采用对数图层,通过黎曼矩阵对数图将所得数据流形嵌入到切线空间中,从而应用欧几里得计算。要了解所建议的GrasNet的多级连接权重,我们使用主成分分析(PCA)算法,而不是复杂的黎曼矩阵反向传播优化器,这使得它的构建和训练极为容易和高效。我们在三种不同的视觉分类任务上评估我们的模型:分别是人脸识别,物体分类和细胞识别。大量的分类结果证明了其可行性和有效性。为了进一步降低学习的几何特征的维数和冗余度,我们设计了一个投影池层。最终采用对数图层,通过黎曼矩阵对数图将所得数据流形嵌入到切线空间中,从而应用欧几里得计算。要了解所建议的GrasNet的多级连接权重,我们使用主成分分析(PCA)算法,而不是复杂的黎曼矩阵反向传播优化器,这使得它的构建和训练极为容易和高效。我们在三种不同的视觉分类任务上评估我们的模型:分别是人脸识别,物体分类和细胞识别。大量的分类结果证明了其可行性和有效性。
更新日期:2020-06-17
down
wechat
bug